Using PIX4Dcatch to capture data to generate a Gaussian Splatting model 

What is Gaussian Splatting? 

Gaussian Splatting is a novel technique for 3D scene reconstruction and rendering that represents a scene as a collection of 3D Gaussians rather than traditional meshes or pointclouds. It allows for highly detailed 3D models with photo-realistic rendering.

How does Gaussian Splatting work? 

Rather than a single algorithm, Gaussian Splatting is a family of techniques, with some prioritizing speed, others focus on rendering quality or geometric accuracy. But all Gaussian Splatting techniques share the same basic primitive to build their models: the 3D Gaussian.

3D Gaussians have two unique advantages over traditional 3D primitives like discrete 3D points. First, thanks to their semi-transparent and gradually changing appearance, large numbers of Gaussians can be blended smoothly, making them ideal for high-quality rendering. The process of generating a rendered image from a set of Gaussians is called “splatting“ because it involves projecting them onto the image plane and spreading (or "splatting") their contribution across multiple pixels. 

Think of spray painting onto a surface. Each spray dot is a "splat" that overlaps with others, forming a smooth, blended result. Similarly, Gaussian Splatting overlays the projected Gaussians to create a seamless final image.

The second key advantage of Gaussians as a building block is mainly relevant for the construction of the model from input images. Thanks to the mathematical properties of a 3D model made of Gaussians, we can precisely predict how changes in their parameters (position, scale, opacity, rotation, and color) will affect the resulting renders. This allows us to iteratively tweak the Gaussian models so that, when seen from the right angle, they look exactly like the real-world photos.

At PIX4D, we combine the strengths of Gaussian Splatting with the reliability and actionability of traditional photogrammetry outputs. Our processing pipeline generates an accurately scaled and georeferenced Gaussian Splatting model, while also producing a point cloud and a mesh built from this model, which benefits from Gaussian Splatting’s ability to reconstruct finer details.

Which projects benefit from the Gaussian Splatting Technique

The Gaussian Splatting technique significantly enhances the accuracy and realism of 3D modeling, particularly when dealing with objects that have intricate geometric details and fine structural elements.

This technique is especially effective for capturing complex shapes, which are often challenging to represent using more traditional approaches. Additionally, it excels in handling thin structures like pipes, wires, and other elongated elements that require high precision to avoid visual artifacts or loss of detail.

This technique provides a smoother, more continuous representation of object surfaces, improving visual fidelity.

Best practices for capturing images to generate a Gaussian Splatting model

To capture high-quality images for Gaussian Splatting (GS) in PIX4Dcatch, follow these best practices to ensure optimal results:

Plan Your Path

• Object-centric scenes yield better results.

• Move in an elliptical path with the phone pointing towards the object.

• If capturing multiple loops around the object, vary the height and viewing perspective.

• Avoid taking multiple images from nearly identical positions and angles, as they add redundancy without improving data quality.

Flat Scenes

• Move in linear paths at a slanted angle (30–40°) to the surface.

• Ensure overlapping paths for complete coverage.

• Avoid capturing only perpendicular views, as this limits the quality of the 3D model.

During Capture

• Move the phone slowly and steadily to avoid motion blur.

• Avoid sudden or unexpected movements that can distort the depth calculations.

• Ensure the object fills the frame while maintaining a consistent distance.

• Use good lighting conditions; avoid shadows and moving objects that can cause inconsistencies in the reconstruction.

• If possible, include LiDAR depth maps, as they significantly improve the Gaussian Splatting results.

Save and Review

• Save the project and review the capture report to check image quality and ensure adequate scene coverage.

Following these steps will help ensure high-quality data for generating a Gaussian Splatting model.

How to process PIX4Dcatch data with Gaussian Splatting on PIX4Dcloud

What are the requirements to generate a Gaussian Splatting model?

The following conditions are needed to process a Gaussian Splatting:

• • Own an active PIX4Dcloud Starter or PIX4Dcloud Pro license.
  • Have enough PIX4Dcloud credits.
  • Install PIX4Dcatch on a mobile device.
  • Upload the images directly from PIX4Dcatch to PIX4Dcloud for processing.
  • The project has a maximum of 2000 images

How to select Gaussian Splatting as an output

Once the project is created,  Gaussian Splatting can be selected when uploading to PIX4Dcloud.

To generate the Gaussian Splatting model, follow the next steps:

1. Go to the project folder and select the project
2. Tap Upload button 
3. Select the upload location
4. Tap Next
5. In the Cloud processing options, turn on Gaussian Splatting.
6. Tap Continue

      7. Tap the Upload button

Credit Consumption

Processing with Gaussian Splatting requires additional processing power and time. Therefore, any project using this technique incurs an additional fee of 5 credits, regardless of the number of images. 

For more information: PIX4Dcloud credit calculator

Viewing and downloading the results in PIX4Dcloud

The project can be accessed in PIX4Dcloud like any other project. If Gaussian Splatting was selected as an output in PIX4Dcatch, the project hierarchy will include a new 3D output called Gaussian Splat. This layer is not displayed by default. The Gaussian Splat model can be downloaded.

Turn on the Gaussian Splat layer to visualize it.